> ## Documentation Index
> Fetch the complete documentation index at: https://docs.slng.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Arcana v3 (Spanish)

> Synthesize Spanish speech using Rime Arcana v3 TTS model.

export const HostingBanner = ({type = "slng", provider, regions = []}) => {
  const isSlng = type === "slng";
  const regionLabel = regions.map(r => r.toUpperCase()).join(", ");
  return <div className={`hosting-banner ${isSlng ? "hosting-banner--slng" : "hosting-banner--thirdparty"}`}>
      <span className="hosting-banner__label">
        {isSlng ? "SLNG Sovereign Hosting" : `3rd Party API Hosted by ${provider}`}
      </span>
      <span className="hosting-banner__text">
        {isSlng ? <>
            On demand in: {regionLabel}.{" "}
            <a href="mailto:support@slng.ai">Request here</a> if you want access
            in any other of our 11 regions.
          </> : <>
            For SLNG Sovereign Hosting in any of our 11 regions{" "}
            <a href="mailto:support@slng.ai">contact us</a>.
          </>}
      </span>
    </div>;
};

<HostingBanner type="slng" regions={["EU"]} />


## OpenAPI

````yaml POST /v1/tts/slng/rime/arcana:3-es
openapi: 3.0.3
info:
  title: SLNG Gateway API - SLNG TTS
  version: 0.1.0
  description: Unified API for speech-to-text and text-to-speech services.
  contact:
    name: SLNG Support
    email: support@slng.ai
servers:
  - url: https://api.slng.ai
    description: Production
  - url: https://stageapi.slng.ai
    description: Staging
security:
  - BearerAuth: []
tags:
  - name: Deepgram Aura 2
    description: Deepgram Aura 2 for conversational voice agents.
  - name: Orpheus English
    description: Orpheus TTS with emotion control.
  - name: Rime Arcana v2
    description: Rime Arcana v2 TTS with multi-language support.
  - name: Rime Arcana v3
    description: Rime Arcana v3 TTS with multilingual support (English, Hindi).
  - name: Rime Coda
    description: Rime Coda TTS for Bahasa Indonesian.
  - name: Inworld Max 1.5
    description: Inworld Max 1.5 for multilingual, expressive synthesis.
paths:
  /v1/tts/slng/rime/arcana:3-es:
    post:
      tags:
        - Rime Arcana v3
      summary: Arcana v3 (Spanish)
      description: Synthesize Spanish speech using Rime Arcana v3 TTS model.
      operationId: rime/arcana:3-es
      parameters:
        - $ref: '#/components/parameters/XRegionSlngArcanaV3Es'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RimeArcana3TtsRequestEs'
            examples:
              basic:
                summary: Basic Spanish synthesis
                value:
                  text: >-
                    Hola desde Rime Arcana v3 Español. Probando la síntesis de
                    texto a voz.
                  speaker: seraphina
      responses:
        '200':
          $ref: '#/components/responses/TtsSynthesisSuccess'
        '400':
          $ref: '#/components/responses/RimeArcanaBadRequest'
        '401':
          $ref: '#/components/responses/ProviderUnauthorized'
        '500':
          $ref: '#/components/responses/RimeArcanaInternalServerError'
        '503':
          $ref: '#/components/responses/ProviderServiceUnavailable'
components:
  parameters:
    XRegionSlngArcanaV3Es:
      name: X-Region-Override
      in: header
      required: false
      description: Target region override. Auto-selected if not provided.
      schema:
        type: string
        enum:
          - eu-north-1
  schemas:
    RimeArcana3TtsRequestEs:
      description: Rime Arcana v3 TTS request for Spanish.
      type: object
      required:
        - speaker
      properties:
        speaker:
          $ref: '#/components/schemas/RimeArcana3SpeakerEs'
        modelId:
          type: string
          default: arcana-3
          description: Rime Arcana v3 model identifier.
        language:
          type: string
          enum:
            - es
          default: es
          description: Language code.
      allOf:
        - $ref: '#/components/schemas/RimeArcanaTtsRequestCommon'
    RimeArcana3SpeakerEs:
      type: string
      description: Voice speaker ID for Rime Arcana v3 Spanish.
      default: seraphina
      enum:
        - aurelio
        - celestino
        - lark
        - luz
        - mar
        - nova
        - pola
        - seraphina
        - sirius
        - ursa
    RimeArcanaTtsRequestCommon:
      type: object
      description: Common Rime Arcana TTS options.
      properties:
        text:
          type: string
          minLength: 1
          description: Text to synthesize.
        modelId:
          $ref: '#/components/schemas/RimeArcanaModelId'
        repetition_penalty:
          type: number
          format: float
          default: 1.5
          description: >-
            The repetition penalty. We do not recommend changing this from the
            default value. Typical range is 1 to 2. Float that penalizes new
            tokens based on whether they appear in the prompt and the generated
            text so far. Values > 1 encourage the model to use new tokens, while
            values < 1 encourage the model to repeat tokens.
        temperature:
          type: number
          format: float
          default: 0.5
          description: >-
            The temperature. We do not recommend changing this from the default
            value. Typical range is 0 to 1. Float that controls the randomness
            of the sampling. Lower values make the model more deterministic,
            while higher values make the model more random. Zero means greedy
            sampling.
        top_p:
          type: number
          format: float
          default: 1
          description: >-
            The top p. We do not recommend changing this from the default value.
            Typical range is 0 to 1. Float that controls the cumulative
            probability of the top tokens to consider. Must be in (0, 1]. Set to
            1 to consider all tokens.
        audioFormat:
          $ref: '#/components/schemas/RimeArcanaAudioFormat'
        sample_rate:
          $ref: '#/components/schemas/RimeArcanaSampleRate'
        speed:
          type: number
          description: Speech rate multiplier (0.25 = half speed, 2.0 = double speed).
          minimum: 0.25
          maximum: 2
          default: 1
      required:
        - text
    AudioBinary:
      type: string
      format: binary
      description: Binary audio data.
    ProviderErrorResponse:
      type: object
      description: >
        Provider error response. Contains error information from the upstream
        provider.

        Common errors include invalid speakers, unsupported languages, or
        malformed requests.
      properties:
        error:
          type: string
          description: >-
            Error type or category (e.g., "TTS service error", "Validation
            error").
          example: TTS service error
        status:
          type: number
          description: >-
            Original HTTP status code from the provider (may differ from gateway
            response code).
          example: 400
        details:
          type: string
          description: >
            Detailed error message from the provider. For TTS errors, this
            typically includes

            the specific validation failure (e.g., invalid speaker ID for the
            selected model/language).
          example: >-
            Rime TTS API error: 400 Bad Request - Invalid argument: Invalid
            speaker: aurelie
      required:
        - error
    RimeArcanaModelId:
      type: string
      description: 'Model: arcana (most realistic, ~150ms), mistv2 (speed & control, ~70ms).'
      enum:
        - arcana
        - arcana-3
        - mistv2
        - mist
      default: arcana
    RimeArcanaAudioFormat:
      type: string
      description: Output audio format as MIME type.
      enum:
        - audio/webm;codecs=opus
        - audio/ogg;codecs=opus
        - audio/mp3
        - audio/wav
        - audio/pcm
        - audio/x-mulaw
      default: audio/wav
    RimeArcanaSampleRate:
      type: integer
      description: Output sample rate in Hz. Values above 24000 are upsampled.
      default: 24000
      enum:
        - 8000
        - 16000
        - 22050
        - 24000
        - 44100
        - 48000
        - 96000
  responses:
    TtsSynthesisSuccess:
      description: Synthesis successful.
      content:
        audio/*:
          schema:
            $ref: '#/components/schemas/AudioBinary'
    RimeArcanaBadRequest:
      description: >
        Rime Arcana TTS bad request. Common causes include invalid speaker ID
        for the

        selected language variant, unsupported model, unsupported audio format,
        or malformed request body.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ProviderErrorResponse'
          examples:
            invalid-speaker:
              summary: Invalid speaker ID
              description: >
                Speaker ID not available for this language variant. Each Arcana
                language

                has specific voices - check the endpoint schema for valid
                speakers.
              value:
                error: TTS service error
                details: >-
                  Rime TTS API error: 400 Bad Request - Invalid argument:
                  Invalid speaker: aurelie
            invalid-speaker-for-language:
              summary: Speaker not available for language
              description: Using a speaker from a different language variant.
              value:
                error: TTS service error
                details: >-
                  Rime TTS API error: 400 Bad Request - Invalid argument:
                  Invalid speaker: astra
            missing-text:
              summary: Missing text field
              value:
                error: Validation error
                details: 'Missing required field: text'
            unsupported-model:
              summary: Unsupported model
              description: The specified modelId is not supported by Rime Arcana.
              value:
                error: TTS service error
                details: 'Rime TTS API error: 400 Bad Request - Unsupported model'
    ProviderUnauthorized:
      description: Invalid or missing API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ProviderErrorResponse'
    RimeArcanaInternalServerError:
      description: >
        Rime Arcana TTS internal error. Note: Some validation errors (e.g.,
        invalid speaker)

        may currently return 500 instead of 400. Check the error details for
        specifics.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ProviderErrorResponse'
          examples:
            processing-error:
              summary: Processing error
              value:
                error: TTS service error
                details: Internal processing error
            invalid-speaker-as-500:
              summary: Invalid speaker (returned as 500)
              description: |
                Invalid speaker errors may currently return 500 instead of 400.
                The details field will indicate the actual validation error.
              value:
                error: TTS service error
                details: >-
                  Rime TTS API error: 400 Bad Request - Invalid argument:
                  Invalid speaker: aurelie
    ProviderServiceUnavailable:
      description: Service unavailable.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ProviderErrorResponse'
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: |
        API key issued by SLNG. Pass as `Authorization: Bearer <token>`.

````